****************************************************
****************************************************
* These commands tell STATA how to interpret things
* 1. cd tells STATA what computer directory you are working in
* 2. "set more off" tells STATA's results screen to scroll nicely
* 3. the log commands tell the computer to save an output file with results 
****************************************************
****************************************************

cd [PATH ON YOUR COMPUTER]
* For example:
* cd I:\

set more off

log using "sample-log.log", replace
log on


****************************************************
****************************************************
* These commands read the raw data into STATA
****************************************************
****************************************************

infix age 1-2 educ 3-4 health 5-6 partyid 7-8 sex 9-10 using "sample_data.dat"


****************************************************
****************************************************
* These commands labels the variables
****************************************************
****************************************************

label variable age "Person's Age (in Years)"
label variable educ "Person's Years of School Completed"
label variable health "Person's Self-Rated Health"
label variable partyid "Person's Party Affiliation"
label variable sex "Person's Sex"


****************************************************
****************************************************
* These commands label each variable's values
****************************************************
****************************************************

label define lab_health 1 "Excellent" 2 "Good" 3 "Fair" 4 "Poor"
label values health lab_health

label define lab_partyid 0 "Strong Democrat" 1 "Not Strong Democrat" 2 "Independent, Near Democrat" 3 "Independent" 4 "Independent, Near Republican" 5 "Not Strong Republican" 6 "Strong Republican" 7 "Other Party"
label values partyid lab_partyid

label define lab_sex 1 "Male" 2 "Female"
label values sex lab_sex


****************************************************
****************************************************
* These commands decalre some values to represent missing data
****************************************************
****************************************************

replace age=. if age==-9
replace educ=. if educ==-9
replace health=. if health==-9
replace partyid=. if partyid==-9
replace sex=. if sex==-9


******************************************************************************************************************
******************************************************************************************************************
* These commands produce frequency distributions for the entire sample
******************************************************************************************************************
******************************************************************************************************************

tab age
tab educ
tab health
tab partyid
tab sex


******************************************************************************************************************
******************************************************************************************************************
* These commands produce frequency distributions separately for Democrats, Independents, and Republicans
******************************************************************************************************************
******************************************************************************************************************

* For Democrats
tab age if partyid>=0 & partyid<=1
tab educ if partyid>=0 & partyid<=1
tab health if partyid>=0 & partyid<=1
tab sex if partyid>=0 & partyid<=1

* For Independents
tab age if partyid>=2 & partyid<=4
tab educ if partyid>=2 & partyid<=4
tab health if partyid>=2 & partyid<=4
tab sex if partyid>=2 & partyid<=4

* For Republicans
tab age if partyid>=5 & partyid<=6
tab educ if partyid>=5 & partyid<=6
tab health if partyid>=5 & partyid<=6
tab sex if partyid>=5 & partyid<=6


******************************************************************************************************************
******************************************************************************************************************
* These commands produce histograms for the entire sample for continuous variables
******************************************************************************************************************
******************************************************************************************************************

hist age
graph export "age_graph.png", as(png) replace

hist educ
graph export "educ_graph.png", as(png) replace


******************************************************************************************************************
******************************************************************************************************************
* These commands produce measures of central tendency and spread for the entire sample for continuous variables
******************************************************************************************************************
******************************************************************************************************************

tabstat age, stat(mean sd min p25 median p75 max n)
tabstat educ, stat(mean sd min p25 median p75 max n)


******************************************************************************************************************
******************************************************************************************************************
* These commands produce measures of central tendency and spread for continuous variables separately by sex
******************************************************************************************************************
******************************************************************************************************************

*For Men
tabstat age if sex==1, stat(mean sd min p25 median p75 max n)
tabstat educ if sex==1, stat(mean sd min p25 median p75 max n)

*For Women
tabstat age if sex==2, stat(mean sd min p25 median p75 max n)
tabstat educ if sex==2, stat(mean sd min p25 median p75 max n)


log off
log close